con un clic
qa-cycle
QA + bugfix cycle until it passes
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Menú
QA + bugfix cycle until it passes
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Full pipeline: evaluation -> spec -> implementation -> review -> QA
Full pipeline: evaluation -> spec -> implementation -> review -> QA
Convenes multiple agents to debate an important decision
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
Convenes multiple agents to debate an important decision
Enriches CLAUDE.md by exploring the project and specializes agents to the real stack
| name | qa-cycle |
| description | QA + bugfix cycle until it passes |
| user-invocable | true |
| workflow | {"version":1,"steps":[{"id":"gate-pre-qa","role":"system","intent":"Run project tests and lint before QA validation.","gate":true,"produces":["test-result","lint-result"]},{"id":"qa-validate","role":"qa","intent":"Validate the implementation against acceptance criteria. Test edge cases and error scenarios. Report bugs found.","requires":["acceptance-criteria","test-result","lint-result"],"produces":["qa-report"],"model-tier":"execution"},{"id":"bugfix","role":"bugfix","intent":"Diagnose and fix bugs reported by QA. Run tests after fixing.","requires":["qa-report"],"produces":["bugfix-result"],"model-tier":"execution"},{"id":"gate-post-qa","role":"system","intent":"Run project tests and lint after QA cycle completes.","gate":true,"produces":["final-test-result","final-lint-result"]}]} |
Runs a QA validation cycle followed by bugfix until all criteria pass clean. Useful for validating implementations without the full build-feature pipeline.
/qa-cycle
Before invoking the QA agent, run the project verification commands. The specific commands are in the "CLI commands" section of CLAUDE.md:
npm test) — record result and outputnpm run lint) — record result and outputInvoke the QA agent using Task tool with model: "sonnet" (execution tier):
.claude/agents/qa.md to assume the QA roleIf QA reports bugs (including test/lint failures), invoke the Bugfix agent using Task tool with model: "sonnet" (execution tier):
.claude/agents/bugfix.md to assume the Bugfix roleReturn to Step 1 (automated verification) to re-validate after the bugfix. Maximum 3 verification-QA-bugfix cycles to prevent infinite loops.
Present the result:
User: /qa-cycle
QA (sonnet) — Cycle 1: 2 of 5 criteria pass. Bug: form validation missing on email field.
Bugfix (sonnet) — Added email regex validation to UserForm component.
QA (sonnet) — Cycle 2: 5 of 5 criteria pass. 0 bugs.
Result: Approved.
When spawning QA or Bugfix agents via the Task tool, always use subagent_type: "general-purpose". Guild agent role names are NOT valid Claude Code subagent_types.
Example:
Task tool with:
subagent_type: "general-purpose"
model: "sonnet"
prompt: "Read .claude/agents/qa.md and assume that role. Then: [task description]"
The model parameter is resolved from the step's model-tier: qa-validate and bugfix use execution→"sonnet".